COVIDAL: A Machine Learning Classifier for Digital COVID-19 Diagnosis in German Hospitals

For the fight against the COVID-19 pandemic, it is particularly important to map the course of infection, in terms of patients who have currently tested SARS-CoV-2 positive, as accurately as possible. In hospitals, this is even more important because resources have become scarce. Although polymerase chain reaction (PCR) and point of care (POC) antigen testing capacities have been massively expanded, they are often very time-consuming and cost-intensive and, in some cases, lack appropriate performance. To meet these challenges, we propose the COVIDAL classifier for AI-based diagnosis of symptomatic COVID-19 subjects in hospitals based on laboratory parameters. We evaluate the algorithm's performance by unique multicenter data with approximately 4,000 patients and an extraordinary high ratio of SARS-CoV-2-positive patients. We analyze the influence of data preparation, flexibility in optimization targets, as well as the selection of the test set on the COVIDAL outcome. The algorithm is compared with standard AI, PCR, POC antigen testing and manual classifications of seven physicians by a decision theoretic scoring model including performance metrics, turnaround times and cost. Thereby, we define health care settings in which a certain classifier for COVID-19 diagnosis is to be applied. We find sensitivities, specificities, and accuracies of the COVIDAL algorithm of up to 90 percent. Our scoring model suggests using PCR testing for a focus on performance metrics. For turnaround times, POC antigen testing should be used. If balancing performance, turnaround times, and cost is of interest, as, for example, in the emergency department, COVIDAL is superior based on the scoring model. © 2023 Association for Computing Machinery.

External Validation of the 4C Mortality Score and the qSOFA for Different Variants of Concerns of SARS-CoV-2 Using Data of the NAPKON Cross-Sectoral Cohort Platform (SUEP)

Background. Numerous predictive clinical scores with varying discriminatory performance have been developed in the context of the current coronavirus disease 2019 (COVID-19) pandemic. To support clinical application, we test the transferability of the frequently applied 4C mortality score (4C score) to the German prospective Cross-Sectoral Platform (SUEP) of the National Pandemic Cohort Network (NAPKON) compared to the non COVID-19 specific quick sequential organ failure assessment score (qSOFA). Our project aims to externally validate these two scores, stratified for the most prevalent variants of concerns (VOCs) of severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) in Germany. Methods. A total of 685 adults with polymerase chain reaction (PCR)-detected SARS-CoV-2 infection were included from NAPKON-SUEP. Patients were recruited from 11/2020 to 03/2022 at 34 university and non-university hospitals across Germany. Missing values were complemented using multiple imputation. Predictive performance for in-hospital mortality at day of baseline visit was determined by area under the curve (AUC) with 95%-confidence interval (CI) stratified by VOCs of SARS-CoV-2 (alpha, delta, omicron) (Figure 1). Figure 1: Study flow chart with inclusion criteria and methodological workflow. Results. Preliminary results suggest a high predictive performance of the 4C score for in-hospital mortality (Table 1). This applies for the overall cohort (AUC 0.813 (95%CI 0.738-0.888)) as well as the VOC-strata (alpha: AUC 0.859 (95%CI 0.748-0.970);delta: AUC 0.769 (95%CI 0.657-0.882);omicron: AUC 0.866 (95%CI 0.724-1.000)). The overall mortality rates across the defined 4C score risk groups are 0.3% (low), 3.2% (intermediate), 11.6% (high), and 49.5% (very high). The 4C score performs significantly better than the qSOFA (Chi2-test: p=0.001) and the qSOFA does not seem to be a suitable tool in this context. Table 1: Discriminatory performance of the 4C Mortality Score and the qSOFA score within the validation cohort NAPKON-SUEP stratified by the Variant of Concerns of SARS-CoV- 2. Conclusion. Despite its development in the early phase of the pandemic and improved treatment, external validation of the 4C score in NAPKON-SUEP indicates a high predictive performance for in-hospital mortality across all VOCs. However, since the qSOFA was not specifically designed for this predictive issue, it shows low discriminatory performance, as in other validation studies. Any interpretations regarding the omicron stratum are limited due to the sample size.

[COVID-19 and endoscopy services]. / COVID-19 und Endoskopieeinheiten: Erfahrungen und Empfehlungen nach 2 Jahren Pandemie.

In 2020, the coronavirus pandemic initially led to a significant decrease in elective endoscopic examinations in Germany. The main reasons for this were the hard lockdown and the lack of personal protective equipment (PPE) and testing procedures. Since then, international recommendations from professional societies on infection control in endoscopy have been published. The extent to which these have been implemented in Germany is unclear: during the 2nd and 3rd waves in 2020/2021, most endoscopy units remained open and the level of adherence to international protection guidelines was high. A uniform "standard procedure" has not yet been published. The exact role and effectiveness of testing procedures to protect patients and staff during endoscopy was unknown, and reliable figures on staff and patient infections acquired/transmitted in endoscopy units in Germany were lacking. Thus, the most important finding of this work is the determined rate of coronavirus disease 2019 (COVID-19) in endoscopy facilities. The data show that the infection rate among staff in German clinics and practices in early 2021 averaged up to 5%; most of these were acquired in the private setting. Clinics with gastroenterological endoscopy units had significantly higher infection rates (10%) than, for example, dental and otolaryngology practices. This result indicates the need for continued PPE efforts. The most important factors for infection safety are fully vaccinated (or recovered) staff and patients, a decreasing prevalence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the use of PPE and-although controversial-the consistent use of screening tests.

COVID-19 und Endoskopieeinheiten : Erfahrungen und Empfehlungen nach 2 Jahren Pandemie COVID-19 and endoscopy servicesExperience and recommendations after 2 years of pandemic

Die Pandemie durch die Coronaviruserkrankung 2019 (COVID-19) hat im Jahr 2020 initial zu einem erheblichen Rückgang elektiver Endoskopien in Deutschland geführt. Maßgeblich hierfür waren besonders der harte Lockdown sowie der Mangel an Schutzausrüstung (PSA) und Testverfahren. Seither erschienen internationale Empfehlungen der Fachgesellschaften zum Infektionsschutz in der Endoskopie. Inwieweit diese in Deutschland umgesetzt wurden, ist unklar: Während der 2. und 3. Welle 2020/2021 blieben die meisten Endoskopieeinheiten geöffnet und wenden seither zahlreiche Schutzmaßnahmen an. Ein einheitliches „Standardvorgehen“ ist bisher nicht publiziert. Die genaue Rolle und Effektivität von Testverfahren zum Schutz von Patienten und Personal während der Endoskopie war bisher nicht bekannt, verlässliche Zahlen über in Endoskopieeinrichtungen in Deutschland erworbene/weitergegebene Infektionen bei Personal und Patienten fehlten bisher. Wichtigstes Ergebnis der Arbeit ist nun die ermittelte COVID-19-Rate in endoskopierenden Einrichtungen. Die Daten zeigen, dass die Infektionsrate bei Mitarbeitern in deutschen Kliniken und Praxen Anfang 2021 im Mittel bis 5 % betrug;die meisten dieser Infektionen wurden im privaten Umfeld erworben. Kliniken mit gastroenterologischer Endoskopie hatten signifikant mehr Infektionsübertragungen (10 %) als z. B. Zahnarzt- und Hals-Nasen-Ohren-Praxen. Daher sind besonders hier zukünftig weiterhin Schutzmaßnahmen nötig. Die wichtigsten Faktoren für die Infektionssicherheit sind vollständig geimpfte (oder genesene) Mitarbeiter und Patienten („2-G“), eine abnehmende Prävalenz von Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) sowie die Anwendung von PSA und – allerdings kontrovers diskutiert – die Durchführung konsequenter Screeningtests.

Ressourcenbedarf bei der chirurgischen Behandlung von COVID‑19-Patienten in der universitären Maximalversorgung Resource requirements in the surgical treatment of COVID‑19 patients at a university clinic of maximum care

Hintergrund Operative Eingriffe bei an „coronavirus disease 2019“ (COVID‑19) erkrankten Patienten sind unter strengen Hygiene- und Schutzmaßnahmen möglich und werden inzwischen regelhaft durchgeführt. In dieser Arbeit soll geprüft werden, mit welchem Mehraufwand dies verbunden ist. Material und Methoden Es erfolgte die strukturierte Auswertung von 71 am Universitätsklinikum Augsburg zwischen dem 01.11.2020 und 31.12.2020 durchgeführten Operationen. Weiterhin erfolgte der Vergleich von zeitlichem, strukturellem und personellem Aufwand zwischen Operationen an COVID‑19-Patienten und Non-COVID‑19-Patienten am Beispiel von vier Eingriffen: transbrachiale Embolektomie, Implantation von Hüfttotalendoprothesen (Hüft-TEP) oder Proximalem Femurnagel Antirotation (PFN-A) und Herzschrittmachern. Ergebnisse Die Schnitt-Naht-Zeiten zwischen den Eingriffen bei an COVID‑19-Erkrankten und Non-COVID-Patienten zeigten bei keinem der vier untersuchten Eingriffe signifikante Unterschiede. Die bei vielen Eingriffen als zeitaufwendig identifizierte postoperative Überwachung im Operationssaal wurde häufig durch postoperative Verlegung auf Intensivstation oder durch die Verwendung lokaler Anästhesieverfahren umgangen. Bei großen Operationen wie Hüft-TEP-Implantation war die Vorbereitungszeit signifikant verlängert. (p = 0,037). Des Weiteren zeigte sich ein signifikant höherer Bedarf an Anästhesiepflegekräften (1,5 vs. 1,0, p = 0,02). Schlussfolgerung Eine Quantifizierung des Mehraufwandes der operativen Versorgung ist durch die ohnehin komplexe Versorgung der COVID‑19-Patienten nur schwer möglich. Allerdings ist davon auszugehen, dass ein erhöhter, durch die Standarderfassung nicht dokumentierter Bedarf an zusätzlichen personellen und strukturellen Ressourcen durch die Materialzubringung von außerhalb des Operationssaales besteht.

[Resource requirements in the surgical treatment of COVID­19 patients at a university clinic of maximum care]. / Ressourcenbedarf bei der chirurgischen Behandlung von COVID­19-Patienten in der universitären Maximalversorgung.

BACKGROUND: Surgical procedures in patients suffering from coronavirus disease 2019 (COVID­19) are possible under strict hygiene and protective measures and are currently carried out regularly. This study examined how much additional work this involves. MATERIAL AND METHODS: A structured evaluation of 71 surgical procedures performed at the Augsburg University Hospital between 1 November 2020 until 31 December 2020 was carried out. The operations on COVID­19 patients were compared to procedures on non-COVID­19 patients with respect to temporal, structural and staff resources, exemplified by four interventions: transbrachial embolectomy, total hip arthroplasty (H-TEP), proximal femoral nail antirotation (PFN-A) and new implantations of cardiac pacemakers. RESULTS: The incision to suture times between the interventions in patients with COVID­19 and non-COVID­19 patients did not show any significant differences in any of the four interventions evaluated. The postoperative monitoring in the operating room, which is identified as time-consuming in many interventions, was often circumvented by postoperative transfer to the intensive care unit or by the use of local anesthetic procedures. For major operations, such as H­TEP, the preparation time was shown to be significantly longer (p = 0.037). Furthermore, there was a significantly higher requirement for anesthesia nursing personnel of 1.5 vs. 1.0 (p = 0.02). CONCLUSION: A quantification of the additional effort of operative treatment is difficult due to the already complex care of COVID­19 patients; however, it can be assumed that there is an increased need for additional human and structural resources due to the supply of material from outside the operating room, which is not documented in the standard recording.

[Bed capacity management in times of the COVID-19 pandemic : A simulation-based prognosis of normal and intensive care beds using the descriptive data of the University Hospital Augsburg]. / Bettenkapazitätssteuerung in Zeiten der COVID-19-Pandemie : Eine simulationsbasierte Prognose der Normal- und Intensivstationsbetten anhand der deskriptiven Daten des Universitätsklinikums Augsburg.

BACKGROUND: Following the regional outbreak in China, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread all over the world, presenting the healthcare systems with huge challenges worldwide. In Germany the coronavirus diseases 2019 (COVID-19) pandemic has resulted in a slowly growing demand for health care with a sudden occurrence of regional hotspots. This leads to an unpredictable situation for many hospitals, leaving the question of how many bed resources are needed to cope with the surge of COVID-19 patients. OBJECTIVE: In this study we created a simulation-based prognostic tool that provides the management of the University Hospital of Augsburg and the civil protection services with the necessary information to plan and guide the disaster response to the ongoing pandemic. Especially the number of beds needed on isolation wards and intensive care units (ICU) are the biggest concerns. The focus should lie not only on the confirmed cases as the patients with suspected COVID-19 are in need of the same resources. MATERIAL AND METHODS: For the input we used the latest information provided by governmental institutions about the spreading of the disease, with a special focus on the growth rate of the cumulative number of cases. Due to the dynamics of the current situation, these data can be highly variable. To minimize the influence of this variance, we designed distribution functions for the parameters growth rate, length of stay in hospital and the proportion of infected people who need to be hospitalized in our area of responsibility. Using this input, we started a Monte Carlo simulation with 10,000 runs to predict the range of the number of hospital beds needed within the coming days and compared it with the available resources. RESULTS: Since 2 February 2020 a total of 306 patients were treated with suspected or confirmed COVID-19 at this university hospital. Of these 84 needed treatment on the ICU. With the help of several simulation-based forecasts, the required ICU and normal bed capacity at Augsburg University Hospital and the Augsburg ambulance service in the period from 28 March 2020 to 8 June 2020 could be predicted with a high degree of reliability. Simulations that were run before the impact of the restrictions in daily life showed that we would have run out of ICU bed capacity within approximately 1 month. CONCLUSION: Our simulation-based prognosis of the health care capacities needed helps the management of the hospital and the civil protection service to make reasonable decisions and adapt the disaster response to the realistic needs. At the same time the forecasts create the possibility to plan the strategic response days and weeks in advance. The tool presented in this study is, as far as we know, the only one accounting not only for confirmed COVID-19 cases but also for suspected COVID-19 patients. Additionally, the few input parameters used are easy to access and can be easily adapted to other healthcare systems.

Status quo after one year of COVID-19 pandemic in otolaryngological hospital-based departments and private practices in Germany.

PURPOSE: The COVID-19 pandemic has affected healthcare systems worldwide. Data on the impact on otolaryngological clinics and private practices is sparse. This study aimed to present data on healthcare worker (HCW) screening, status of HCW, pre-interventional testing, the use of personal protective equipment (PPE) and the economic impact of the pandemic. METHODS: Otolaryngological private practices and hospital-based departments were surveyed nationwide using an online questionnaire. Participating facilities were recruited via the German Society for Oto-Rhino-Laryngology and the German Association for Otolaryngologists in Bavaria. RESULTS: 365 private practices (2776 employees) and 65 hospitals (2333 employees) were included. Significantly more hospitals (68.7%) than practices (40.5%) performed pre-interventional testing in their outpatients (p < 0.00). Most inpatients were tested in practices and hospitals (100.0% and 95.0%; p = 0.08). HCW screening was performed in 73.7% of practices and in 77.3% of hospitals (p = 0.54). Significantly more HCW infections were reported in private practices (4.7%) than in hospital (3.6%; p = 0.03). The private or home environment was the most frequent source of infection among HCW in hospitals (44%) and practices (63%). The use of PPE increased over the course of the pandemic. The number of procedures and the revenue decreased in 2020. CONCLUSION: The rate of pre-interventional testing among outpatients in otolaryngological practices is low and HCW infections were found to be more frequent in practices than in hospitals. In addition, a high rate of infections in otolaryngological HCW seems to stem from the private or home environment.